Our research group focuses on key scientific problems in the detection, processing, and recognition of biomedical signals. We conduct research in machine learning, spatial multi-omics, computational mass spectrometry, mass spectrometry imaging, molecular network modeling, and healthcare big data analysis. The main goal is to develop computational methods and analytical tools for complex biomedical data, with an emphasis on improving the interpretation of metabolomics, mass spectrometry imaging, and multimodal spatial omics data.

In methodological research, the group focuses on mass spectrometry data preprocessing, feature extraction, molecular annotation, spatial signal reconstruction, and multimodal data integration. By combining machine learning, statistical modeling, and network analysis, we aim to establish computational models that can characterize molecular spatial distributions, metabolic regulatory relationships, and disease-associated changes. In application-oriented research, the group studies diseases such as Alzheimer’s disease, hepatocellular carcinoma, diabetic kidney disease, and nasopharyngeal carcinoma, with the aim of discovering disease-related molecular markers, analyzing spatial metabolic abnormalities, and investigating disease mechanisms through multi-omics data.

Through interdisciplinary collaboration among electronic information, artificial intelligence, analytical chemistry, life sciences, and medicine, the group seeks to advance computational mass spectrometry and spatial omics analysis methods, and to provide new data analysis technologies for disease mechanism research, early diagnosis, and precision medicine.